Thesis Data Analysis

Introduction

The variables included in the data set are:

Field	Description
AmountWeek	How many cups of coffee do you typically consume weekly?
AmountOutMonth	How frequently do you drink out-of-home per month on average?
MoneyCoffee	How much money on average do you estimate you spend on coffee per month?
MoneyGroceries	How much on average do you spend on general groceries per month?
Machine	How do you brew your coffee at home?
Brand change	How often do you switch between coffee brands?
Purchase location	Where do you usually purchase your coffee?
Supermarket_Positive_Reasons	When you purchase coffee from the supermarket what are your main reasons for doing so?
Supermarket_Negative_Reasons	What would be reasons why you would not purchase coffee from the supermarket?
Criteria_Type_Coffee	What are your main criteria’s or evaluation points for choosing the type of coffee?
KnowledgeCoffee	How would you describe your knowledge level regarding coffee in general?
Purchase_Price	I believe that the ____ is important to my decision on which coffee to purchase.
Purchase_Sustainability	I believe that the ____ is important to my decision on which coffee to purchase.
Purchase_Sustainability	I believe that the ____ is important to my decision on which coffee to purchase.
Purchase_Fairtrade	I believe that the ____ is important to my decision on which coffee to purchase.
Purchase_Packaging	I believe that the ____ is important to my decision on which coffee to purchase.
Frequency_Specialty	How often do you drink specialty coffee?
Subscription_Likely	How likely are you to have an online subscription for (specialty) coffee?
Subscription_Not_Likely	What is the number one reasons why you would be hesitant?
App_Likely	How likely are you to value and use an app for your online subscription?
Gender	What is your gender?
AgeCategory	What is your age category?
Occupation	What is your occupational status?
Education	What level of education have you completed?
Home	How would you describe the place you currently live in?

Univariate descriptions - Categorical variables

Age category

Age Category	Absolute	Relative
< 18	2	0.89%
18-25	64	28.57%
25-45	99	44.20%
45-60	48	21.43%
> 60	11	4.91%

Home

Home	Absolute	Relative
Rural (Town)	23	10.27%
Suburbs	18	8.04%
Urban (City)	183	81.70%

Gender

Gender	Absolute	Relative
Female	147	65.62%
Male	75	33.48%
Other	2	0.89%

Education

Education	Absolute	Relative
Elementary school	3	1.34%
High school	21	9.38%
Associate degree	18	8.04%
Bachelor’s degree	122	54.46%
Master	56	25.00%
Phd	4	1.79%

Machine

Machine	Absolute	Relative
Aeropress	1	0.45%
CupMachine	72	32.14%
Espresso machine	71	31.70%
Filter machine	47	20.98%
French press	8	3.57%
Instant coffee	5	2.23%
Moka pot	16	7.14%
V60	4	1.79%

Brand choose

Brand choice	Absolute	Relative
Never	73	32.59%
Sometimes	128	57.14%
Very often	20	8.93%
Every time	3	1.34%

Purchase Method

Purchase Method	Absolute	Relative
E-commerce	38	16.96%
Online subscription	9	4.02%
Specialty stores or cafés	27	12.05%
The supermarket	150	66.96%

Multiple option answers:

Reasons buying from the supermarket

Reason	Frequency
Convenience	1
I am satisfied with the product	39
I do not have special stores near where I live	8
I do not purchase coffee from the supermarket	1
Other	1
Price	14
Time-saving	32
Convenience	49
I am satisfied with the product	49
I do not have special stores near where I live	8
I do not purchase coffee from the supermarket	39
Other	2
Price	55
Time-saving	22

Reasons for not buying from the supermarket

Reason	Frequency
Better quality elsewhere	17
I don’t buy from supermarkets	1
Lack of sustainable options	4
Not enough variety	15
Not wanting to support big cooperations	8
Better quality elsewhere	73
I don’t buy from supermarkets	6
It is not fresh	15
Lack of sustainable options	4
No reason	98
Not enough variety	13
Not wanting to support big cooperations	13
Price	2

Criteria for choosing the type of coffee

Reason	Frequency
Better quality elsewhere	17
I don’t buy from supermarkets	1
Lack of sustainable options	4
Not enough variety	15
Not wanting to support big cooperations	8
Better quality elsewhere	73
I don’t buy from supermarkets	6
It is not fresh	15
Lack of sustainable options	4
No reason	98
Not enough variety	13
Not wanting to support big cooperations	13
Price	2

Purchase decisions 1-5

Price

Purchase decision - price	Absolute	Relative
1	24	10.71%
2	54	24.11%
3	54	24.11%
4	51	22.77%
5	41	18.30%

Sustainability

Purchase decision - sustainability	Absolute	Relative
1	18	8.04%
2	36	16.07%
3	82	36.61%
4	56	25.00%
5	32	14.29%

Certificates

Purchase decision - certificate	Absolute	Relative
1	42	18.75%
2	63	28.12%
3	74	33.04%
4	34	15.18%
5	11	4.91%

Fairtrade

Purchase decision - fairtrade	Absolute	Relative
1	21	9.38%
2	35	15.62%
3	76	33.93%
4	60	26.79%
5	32	14.29%

Packaging

Purchase decision - packaging	Absolute	Relative
1	68	30.36%
2	62	27.68%
3	44	19.64%
4	36	16.07%
5	14	6.25%

Combined data

Importance	Price	Sustainability	Certificates	Fairtrade	Packaging
1	42	24	18	42	21
2	63	54	36	63	35
3	74	54	82	74	76
4	34	51	56	34	60
5	11	41	32	11	32

Frequency specialty coffee consumption

Frequency coffee consumption	Absolute	Relative
I do (did) not know what this is	53	23.66%
Never	40	17.86%
Only in cafes	46	20.54%
Sometimes	61	27.23%
Always	24	10.71%

Reasons for not being likely to set up a subscription

Reason	Frequency
I am happy with my coffee now	2
I do not consume enough coffee at home	5
I do not like being stuck with subscriptions	46
No reason	3
Other	3
The packaging that is required for delivery	10
The price	42
I already have a subscription	9
I am happy with my coffee now	105
I do not consume enough coffee at home	17
I do not like being stuck with subscriptions	64
No reason	11
Other	1
The packaging that is required for delivery	4
The price	13

Univariate descriptions - Numerical variables

Amount coffe consumed weekly

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   1.00   10.00   15.50   18.81   25.00   70.00

Amount per month out of house

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  0.000   2.000   5.000   8.107  10.000  40.000

Money coffee

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   1.00   10.00   20.00   25.38   35.00  120.00

Money groceries

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    0.0   157.5   200.0   247.3   300.0   900.0

Subscription likely

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   1.00    1.00    3.00    3.79    6.00   10.00

App likely

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  1.000   1.000   3.000   4.179   7.000  10.000

Boxplots

Parametric testing

H_0 <- There is no association between the two variables.
H_a <- There is a association.

Age - Amount coffee drank


    Pearson's Chi-squared test

data:  AmountWeek and AgeCategory
X-squared = 254.16, df = 136, p-value = 0.000000003461


    Pearson's Chi-squared test with simulated p-value (based on 500
    replicates)

data:  AmountWeek and AgeCategory
X-squared = 254.16, df = NA, p-value = 0.003992

Education - Amount coffee drank


    Pearson's Chi-squared test

data:  AmountWeek and Education
X-squared = 236.72, df = 170, p-value = 0.000546


    Pearson's Chi-squared test with simulated p-value (based on 500
    replicates)

data:  AmountWeek and Education
X-squared = 236.72, df = NA, p-value = 0.03992

Gender - Amount coffee drank


    Pearson's Chi-squared test

data:  AmountWeek and Gender
X-squared = 71.44, df = 68, p-value = 0.3643


    Pearson's Chi-squared test with simulated p-value (based on 500
    replicates)

data:  AmountWeek and Gender
X-squared = 71.44, df = NA, p-value = 0.2894

Home - Amount coffee drank


    Pearson's Chi-squared test

data:  AmountWeek and Home
X-squared = 68.057, df = 68, p-value = 0.4753


    Pearson's Chi-squared test with simulated p-value (based on 500
    replicates)

data:  AmountWeek and Home
X-squared = 68.057, df = NA, p-value = 0.501

App - Age


    Pearson's Chi-squared test

data:  App_Likely and AgeCategory
X-squared = 53.162, df = 36, p-value = 0.03254


    Pearson's Chi-squared test with simulated p-value (based on 500
    replicates)

data:  App_Likely and AgeCategory
X-squared = 53.162, df = NA, p-value = 0.04192

Coffee knowledge - Age


    Pearson's Chi-squared test

data:  KnowledgeCoffee and AgeCategory
X-squared = 151.89, df = 36, p-value = 0.0000000000000003491


    Pearson's Chi-squared test with simulated p-value (based on 500
    replicates)

data:  KnowledgeCoffee and AgeCategory
X-squared = 151.89, df = NA, p-value = 0.001996

Coffee knowledge - Purchase location


    Pearson's Chi-squared test

data:  KnowledgeCoffee and PurchaseLocation
X-squared = 35.066, df = 27, p-value = 0.1372


    Pearson's Chi-squared test with simulated p-value (based on 500
    replicates)

data:  KnowledgeCoffee and PurchaseLocation
X-squared = 35.066, df = NA, p-value = 0.1537

Relationships

Regressions


Call:
lm(formula = Subscription_Likely ~ KnowledgeCoffee)

Residuals:
    Min      1Q  Median      3Q     Max 
-3.8949 -2.2229 -0.5541  2.1059  7.1115 

Coefficients:
                Estimate Std. Error t value Pr(>|t|)    
(Intercept)      1.88533    0.52658   3.580 0.000421 ***
KnowledgeCoffee  0.33439    0.08723   3.833 0.000165 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1

Residual standard error: 2.607 on 222 degrees of freedom
Multiple R-squared:  0.06208,   Adjusted R-squared:  0.05785 
F-statistic: 14.69 on 1 and 222 DF,  p-value: 0.0001647

Incl categorical variables as dummies

Cooks distance –> outliers